Larynx

by Rhasspy

Rhasspy's predecessor TTS — Tacotron-style models for offline assistants.

TL;DR

Rhasspy's predecessor TTS — Tacotron-style models for offline assistants.

Best for legacy Rhasspy deployments — superseded by Piper for new installs. Pricing: free (MIT).

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free (MIT)
Platforms
Linux, Raspberry Pi

What it is

Larynx is the predecessor to Piper from the Rhasspy ecosystem. Still used in some legacy Rhasspy / Mycroft deployments. MIT-licensed. Consent posture: synthetic-only.

Best for: Legacy Rhasspy deployments — superseded by Piper for new installs.
Watch out for: Largely superseded by Piper; some languages still only available through Larynx.

Install / use

pip install larynx

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supported6
HIPAA eligibleNo

Larynx vs Whipscribe

FeatureLarynxWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree (MIT)free beta
Speaker diarization—Yes
Word timestamps—Yes
Streaming—No
Languages699
PlatformsLinux, Raspberry PiWeb, API, MCP

Alternatives to Larynx

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.